One-click install
npx skills add https://github.com/KaihuaTang/Index.skill --skill index-update
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: index-update
Source: https://github.com/KaihuaTang/Index.skill/tree/main/.claude/skills/index-update
Command: npx skills add https://github.com/KaihuaTang/Index.skill --skill index-update

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve?

This Skill solves the problem of turning “already read” notes and chat logs into a structured, layered long-term knowledge base so you can retrieve better answers later.

Core Features & Use Cases

  • Archives read inputs safely: Moves read notes from _new/ to deep/ and chat logs from _chat/ to deep/ without overwriting existing files.
  • Extracts and organizes knowledge: Extracts multiple discrete knowledge items and stores them into memory/ under the correct category (Factual / Procedural / Conditional / Metacognitive) using index navigation.
  • Updates persona conservatively: Detects explicit persona-related requests from user messages and updates persona.md accordingly before extracting knowledge.
  • Layered index for fast retrieval: Uses memory/memory-index.md and each category’s _local_index.md to update or create keyword entries efficiently.

Quick Start

Run /index-update to archive all marked-as-read notes and chats, then extract and index new knowledge into your layered Obsidian memory vault.

Frequently Asked Questions about index-update

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I organize read notes and chat logs into a structured Obsidian memory vault?

To organize read notes and chat logs into an Obsidian memory vault, this Skill archives inputs marked "已读" from `_new/` and `_chat/` into `deep/` without overwriting files, extracting reusable knowledge items into a layered `memory/` index.

What is the best way to extract knowledge items from Obsidian notes into hierarchical categories?

Extracting knowledge items from Obsidian notes into hierarchical categories is done by archiving read inputs and sorting discrete items into Factual, Procedural, Conditional, or Metacognitive folders using `_local_index.md` for layered navigation.

Can I update my persona settings automatically when archiving chat logs in Obsidian?

Yes, you can update persona settings when archiving chat logs in Obsidian. The Skill conservatively detects explicit persona-related requests from user messages and updates `persona.md` accordingly before extracting knowledge.

Does this knowledge management workflow require specific folder structures for chat log archiving?

Yes, this knowledge management workflow requires specific folder structures for chat log archiving. Users must maintain an Obsidian vault with `_new/` notes, `_chat/` transcripts, and a `deep/` directory for safe archiving.

How to safely move read notes in Obsidian without overwriting existing memory files?

To safely move read notes in Obsidian without overwriting existing memory files, the Skill performs deterministic file operations to relocate marked inputs from `_new/` to `deep/` and updates the `memory/memory-index.md` without data loss.

Why are my checked "已读" markers not triggering the memory indexing process?

Checked "已读" markers fail to trigger the memory indexing process if notes are not placed in the required `_new/` or `_chat/` directories, or if the hierarchical `memory/` folder structure is missing for knowledge extraction.